HPMF: Hypergraph-Guided Prototype Mining Framework for Few-Shot Object Detection in Remote Sensing Images
Li Y. Hao M. Ma J. Temirbayev A. Li Y. Lu S. Shang C. Shen Q.
2025Institute of Electrical and Electronics Engineers Inc.
IEEE Transactions on Geoscience and Remote Sensing
2025#63
Few-shot object detection (FSOD) within remote sensing imagery has achieved great advancements in recent years. However, most existing methods are facing one key challenge while handling remote sensing images: many unlabeled instances in few-shot images are treated as background, which tends to degrade the generalization of the trained model severely. This article presents hypergraph-guided prototype mining framework (HPMF), an HPMF that addresses the challenge through joint optimization from three perspectives. The first is hierarchical reference mining (HRM) which constructs a class-instance dual-driven prototype space that enables mining the unlabeled instances via cross-hierarchical similarity fusion. The second is a robust pseudobox estimator (RPE) that generates high-quality pseudobounding boxes for the HRM-mined instances via adaptive density clustering and multistatistic aggregation. The third is a hypergraph-guided decoder (HGD) that introduces hypergraphs into the transformer decoder for group semantic modeling, enhancing high-order semantic association and similarity of instance features, thereby further improving the mining performance of the HRM module. Extensive experiments under various settings show that the proposed HPMF outperforms state-of-the-art methods consistently across multiple widely adopted remote sensing FSOD benchmarks such as DIOR, NWPU-VHR10 v2, and HRRSD.
Few-shot learning , object detection , prototype learning , remote sensing imagery
Text of the article Перейти на текст статьи
Northwestern Polytechnical University, School of Software, Xi’an, 710129, China
Northwestern Polytechnical University, School of Computer Science, Xi’an, 710129, China
Al-Farabi Kazakh National University, Almaty, 050038, Kazakhstan
Nanyang Technological University, School of Computer Science and Engineering, Jurong West, 050038, Singapore
Aberystwyth University, Department of Computer Science, Aberystwyth, SY23 3DB, United Kingdom
Northwestern Polytechnical University
Northwestern Polytechnical University
Al-Farabi Kazakh National University
Nanyang Technological University
Aberystwyth University
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026